Unsupervised Palm Vein Image Segmentation

Safronova, Ekaterina; Pavelyeva, E. A.

doi:10.51130/graphicon-2020-2-3-40

Cited by 4 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A preprocessed set of images from the CASIA multi-spectral palmprint image database [5] was selected as the training and testing data set [10,11]. In total, this set contains 200 different classes (images of the right and left hands of 100 people) with 5 to 6 images of the size of 128×128 pixels in each class (see Fig.…”

Section: Preprocessed and Segmented Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Palm Vein Identification Based on Vein Segmentation and Triplet Loss Function

Trofimov

Pavelyeva

2021

Proceedings of the 31th International Conference on Computer Graphics and Vision. Volume 2

Self Cite

View full text Add to dashboard Cite

In this article the new neural network algorithm for palm vein identification using the triplet loss function is proposed. The neural network model is based on the VGG16 architecture. The similarity learning problem instead of the classification problem is considered. The number of image classes is assumed to be unknown so at the output of the neural network the feature vector is obtained, and then for the pair of palm vein images the distance between them is calculated. Minimization of triplet loss function while training leads to the decrease in distances between the images of the same class, while the distances between the images of different classes increase. The neural network was trained using preprocessed and segmented images from CASIA multi-spectral palmprint image database. The use of segmentation information for palm vein recognition improves the recognition results. Experimental results demonstrate the effectiveness of the proposed method. The value of EER=0.0084 is obtained.

show abstract

Section: Preprocessed and Segmented Datasetmentioning

confidence: 99%

“…The segmentation process is described in [11]. The vein structure is detected using unsupervised learning approach based on W-Net [12] architecture, that ties together into a single autoencoder two fully convolutional neural network architectures, each similar to the U-Net.…”

Section: Preprocessed and Segmented Datasetmentioning

confidence: 99%

Palm Vein Identification Based on Vein Segmentation and Triplet Loss Function

Trofimov

Pavelyeva

2021

Proceedings of the 31th International Conference on Computer Graphics and Vision. Volume 2

Self Cite

View full text Add to dashboard Cite

show abstract

“…Vein pattern images can be acquired without direct contact with the hand [1]. Compared to other biometric techniques, palm vein is difficult to fake or change because each person has unique patterns of veins [2] and veins are usually not visible to others [3]. Therefore, palm vein recognition provides several advantages in terms of convenience during acquisition, is more hygienic, and provides a low risk of fake or theft.…”

Section: Introductionmentioning

confidence: 99%

Contactless Biometric Based on Palm Vein Recognition Using Wavelet and Local Line Binary Patterns

Sari,

Bantun

2023

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

To support the roadmap for coexistence with Covid-19, contactless biometrics is needed as an individual identity verification technology in daily activities such as control systems, recording attendance at offices/schools/agencies and access rights to a room. An example of contactless biometrics is palm vein based biometrics. Because it is contactless, this biometric system does not require direct contact between the user and the sensor device, thus providing several advantages in terms of comfort during acquisition and is more hygienic. In the palm vein recognition system, the palm vein pattern can be considered as a texture feature. Therefore, this study proposes a contactless biometric system based on palm vein recognition using the Local Line Binary Pattern method for extracting texture features of palm vein images resulting from the decomposition of 2D Wavelet Transformation, so as to produce a texture descriptor that is small and compatible with the texture characteristics of thin veins. The proposed texture feature extraction method has been tested using the Fuzzy k-NN classification method on 600 palm images with a CRR accuracy of 95.0% with a computation time of 0.057 seconds.

show abstract

“…The principal curvatures method shows great performance in biometric segmentation (Tikhonova and Pavelyeva, 2020), (Safronova and Pavelyeva, 2020), (Choi et al, 2009). This method is based on calculating the eigenvalues and eigenvectors of Hessian matrix at the target points.…”

Section: Introductionmentioning

confidence: 99%

Human Image Matting Based on Convolutional Neural Network and Principal Curvatures

Sagindykov

Pavelyeva

2021

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Image matting often requires advanced image processing, especially in conditions, when small details such as hair are present in the image. In this article the hybrid method for human image matting based on convolutional neural network and principal curvatures is proposed. The U-Net based neural network is used to predict a rough foreground segmentation mask. Then the obtained foreground mask is refined by principal curvatures method to process the elongated hair-like structures. Test results show that the proposed method can improve the coarse human segmentation.

show abstract

Unsupervised Palm Vein Image Segmentation

Cited by 4 publications

References 24 publications

Palm Vein Identification Based on Vein Segmentation and Triplet Loss Function

Palm Vein Identification Based on Vein Segmentation and Triplet Loss Function

Contactless Biometric Based on Palm Vein Recognition Using Wavelet and Local Line Binary Patterns

Human Image Matting Based on Convolutional Neural Network and Principal Curvatures

Contact Info

Product

Resources

About